L

Bilingual Embedding Large

Jun 2024
LBilingual Embedding Large
Compare in
on
self-host onlyprice
46.9MTEB English v2
Jun 2024released
1,024Dimensions
1K tokensMax input
en, frLanguages

Rankingconfiguration unstated?

Full ranking →
1F2LLM v2 14B86.12F2LLM v2 8B85.43F2LLM v2 4B85.34F2LLM v2 1.7B855F2LLM v2 0.6B84.1
···
22Multilingual E5 Large Instruct69.423Bilingual Embedding Large69.224NV Embed v169.1

Strong at

C
Embeddings & Retrieval#122 of 200

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

Benchmarks

in Embeddings & Retrieval
MTEB Persian v2 · Reranking · Persian69.6#29
JMTEB v2 · Clustering · Japanese48.7#40
JMTEB v2 · STS · Japanese82.7#23
LongEmbed · Mean over tasks · English40.5#70
LongEmbed · Mean over task types · English40.5#70
LongEmbed · Retrieval · English40.5#70
MTEB German v1 · Mean over tasks · German56#13
MTEB German v1 · Mean over task types · German55.3#13
MTEB German v1 · Clustering · German34.9#23
MTEB German v1 · Retrieval · German50.5#21
MTEB German v1 · Classification · German68.9#27
MTEB German v1 · STS · German75.9#3
MTEB German v1 · Pair Classification · German56.3#13
MTEB German v1 · Reranking · German45.3#44
MTEB Europe v1 · Retrieval · multilingual (25 languages)54.9#25
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)86.6#48
MTEB Europe v1 · Classification · multilingual (23 languages)60.6#21
MTEB Europe v1 · Clustering · multilingual (29 languages)42.2#50
MTEB Europe v1 · Instruction Reranking · English-3#164
MTEB Europe v1 · Pair Classification · multilingual (11 languages)89#21
MTEB Europe v1 · Reranking · multilingual (12 languages)56.9#61
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)16.8#48
MTEB French v1 · Retrieval · multilingual (2 languages)57.2#22
MTEB French v1 · Reranking · French79.8#27
MTEB French v1 · Classification · French69.2#23
MTEB French v1 · Summarization · French30.3#65
MTEB French v1 · Pair Classification · French63.8#41
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)67.4#12
MTEB Indic v1 · Mean over task types · multilingual (25 languages)66.7#13
MTEB Indic v1 · Classification · multilingual (8 languages)65.7#15
MTEB Indic v1 · Retrieval · multilingual (14 languages)82.7#13
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)76.3#11
MTEB Indic v1 · Reranking · multilingual (2 languages)84.8#42
MTEB Indic v1 · Pair Classification · Hindi72.3#54
MTEB Indic v1 · STS · multilingual (13 languages)45.9#38
MTEB Indic v1 · Clustering · multilingual (21 languages)39.1#39
MTEB Korean v2 · Reranking · Korean49.3#45
MTEB Korean v2 · Classification · Korean59.1#25
MTEB Dutch v1 · Mean over tasks · Dutch56.2#27
MTEB Dutch v1 · Mean over task types · Dutch63#24
MTEB Dutch v1 · Classification · Dutch62.6#25
MTEB Dutch v1 · Clustering · Dutch36.3#32
MTEB Dutch v1 · Retrieval · Dutch57.5#37
MTEB Dutch v1 · STS · Dutch82.5#14
MTEB Dutch v1 · Multilabel Classification · Dutch36.6#27
MTEB Dutch v1 · Pair Classification · Dutch77#36
MTEB Dutch v1 · Reranking · Dutch88.6#52
MTEB Polish v1 · Pair Classification · Polish85.9#17
MTEB Polish v1 · Classification · Polish61.8#27
MTEB Polish v1 · STS · Polish71#2
MTEB Portuguese v1 · Multilabel Classification · Portuguese20.8#60
MTEB Law v1 · Mean over tasks · multilingual (3 languages)52.3#45
MTEB Law v1 · Mean over task types · multilingual (3 languages)52.3#45
MTEB Law v1 · Retrieval · multilingual (3 languages)52.3#45
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)53.5#34
MTEB Medical v1 · Mean over task types · multilingual (10 languages)55.6#30
MTEB Medical v1 · Retrieval · multilingual (10 languages)54.9#37
MTEB Medical v1 · Clustering · English36.5#84
MTEB Medical v1 · Reranking · Mandarin Chinese75.5#69
FollowIR · Mean over tasks · English-3#164
FollowIR · Mean over task types · English-3#164
FollowIR · Instruction Reranking · English-3#164
MTEB Spanish v1 · Pair Classification · Spanish68#51
MTEB Spanish v1 · Reranking · Spanish51.7#48
MTEB Thai v1 · Clustering · Thai46.9#44
MTEB Thai v1 · Pair Classification · Thai73.6#45
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)41.2#36
MTEB Scandinavian v1 · Classification · multilingual (6 languages)62.8#24
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)64.8#94
MTEB Russian v1.1 · Classification · Russian61.2#41
MTEB Russian v1.1 · STS · Russian75.5#9
MTEB Russian v1.1 · Reranking · Russian63.5#39
MTEB Russian v1.1 · Clustering · Russian57.4#31
MTEB Russian v1.1 · Pair Classification · Russian57.9#59
MTEB Russian v1.1 · Multilabel Classification · Russian39.7#28
RTEB French beta · Mean over tasks · multilingual (2 languages)39.4#73
RTEB German beta · Mean over tasks · German48.1#64
RTEB Law beta · Mean over tasks · multilingual (4 languages)41.2#78
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)79.8#42
MTEB multilingual v2 · Retrieval · multilingual (120 languages)55.1#66
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)73.6#20
MTEB multilingual v2 · Instruction Reranking · English-3#164
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)22.4#45
MTEB multilingual v2 · Reranking · multilingual (22 languages)61.4#57

FAQ

How much does Bilingual Embedding Large cost?›

There is no per-unit API price: self-host only.

Is Bilingual Embedding Large free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is Bilingual Embedding Large, and what is it best at?›

#122 of 200 in Embeddings.

Is Bilingual Embedding Large better than Multilingual E5 Large Instruct?›

On MTEB French v1 · Classification · French, Bilingual Embedding Large scores 69.2 vs 69.4 — about the same.

When was Bilingual Embedding Large released? Is there a newer version?›

Released 2024-06-24. It is the current version in its line.

Is Bilingual Embedding Large open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Bilingual Embedding Large locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is Bilingual Embedding Large?›

Bilingual Embedding Large is an open-weights embeddings & retrieval model from Lajavaness, released Jun 2024.

What are the best alternatives to Bilingual Embedding Large?›

E5 Mistral 7B Instruct (better), F2LLM v2 8B (open weights).